OALL/details_meta-llama__Llama-2-13b-hf
收藏数据集概述
数据集是在评估模型 meta-llama/Llama-2-13b-hf 的过程中自动创建的。该数据集包含 136 个配置,每个配置对应一个评估任务。
数据集结构
- 数据集从 1 次运行中创建。每次运行可以在每个配置中找到一个特定的分割,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 一个额外的配置 "results" 存储所有运行的聚合结果。
数据加载示例
python from datasets import load_dataset data = load_dataset("OALL/details_meta-llama__Llama-2-13b-hf", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
以下是 2024-05-11T15:02:29.953291 运行的最新结果:
python { "all": { "acc_norm": 0.36124238506911754, "acc_norm_stderr": 0.03742598350141828, "acc": 0.5062872270019855, "acc_stderr": 0.012866108021218212 }, "community|acva:Algeria|0": { "acc_norm": 0.5384615384615384, "acc_norm_stderr": 0.035791543525445696 }, "community|acva:Ancient_Egypt|0": { "acc_norm": 0.07301587301587302, "acc_norm_stderr": 0.014681822387231072 }, "community|acva:Arab_Empire|0": { "acc_norm": 0.3132075471698113, "acc_norm_stderr": 0.028544793319055326 }, "community|acva:Arabic_Architecture|0": { "acc_norm": 0.4358974358974359, "acc_norm_stderr": 0.035601666623466345 }, "community|acva:Arabic_Art|0": { "acc_norm": 0.38461538461538464, "acc_norm_stderr": 0.03492896993742304 }, "community|acva:Arabic_Astronomy|0": { "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.03581804596782233 }, "community|acva:Arabic_Calligraphy|0": { "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.03131846503821582 }, "community|acva:Arabic_Ceremony|0": { "acc_norm": 0.5351351351351351, "acc_norm_stderr": 0.036769369509486984 }, "community|acva:Arabic_Clothing|0": { "acc_norm": 0.5435897435897435, "acc_norm_stderr": 0.03576123096991214 }, "community|acva:Arabic_Culture|0": { "acc_norm": 0.3128205128205128, "acc_norm_stderr": 0.033287550657248546 }, "community|acva:Arabic_Food|0": { "acc_norm": 0.5641025641025641, "acc_norm_stderr": 0.03560166662346635 }, "community|acva:Arabic_Funeral|0": { "acc_norm": 0.4, "acc_norm_stderr": 0.050529115263991134 }, "community|acva:Arabic_Geography|0": { "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "community|acva:Arabic_History|0": { "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.03384487217112063 }, "community|acva:Arabic_Language_Origin|0": { "acc_norm": 0.5157894736842106, "acc_norm_stderr": 0.05154534179593067 }, "community|acva:Arabic_Literature|0": { "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.04166567577101579 }, "community|acva:Arabic_Math|0": { "acc_norm": 0.3435897435897436, "acc_norm_stderr": 0.03409627301409856 }, "community|acva:Arabic_Medicine|0": { "acc_norm": 0.4896551724137931, "acc_norm_stderr": 0.04165774775728763 }, "community|acva:Arabic_Music|0": { "acc_norm": 0.2733812949640288, "acc_norm_stderr": 0.03794007121533619 }, "community|acva:Arabic_Ornament|0": { "acc_norm": 0.5282051282051282, "acc_norm_stderr": 0.03584074674920833 }, "community|acva:Arabic_Philosophy|0": { "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "community|acva:Arabic_Physics_and_Chemistry|0": { "acc_norm": 0.5384615384615384, "acc_norm_stderr": 0.03579154352544572 }, "community|acva:Arabic_Wedding|0": { "acc_norm": 0.4307692307692308, "acc_norm_stderr": 0.0355521325205876 }, "community|acva:Bahrain|0": { "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.07491109582924914 }, "community|acva:Comoros|0": { "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.07216392363431012 }, "community|acva:Egypt_modern|0": { "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.05149958471474543 }, "community|acva:InfluenceFromAncientEgypt|0": { "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.03509545602262037 }, "community|acva:InfluenceFromByzantium|0": { "acc_norm": 0.7172413793103448, "acc_norm_stderr": 0.037528339580033376 }, "community|acva:InfluenceFromChina|0": { "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.0317493043641267 }, "community|acva:InfluenceFromGreece|0": { "acc_norm": 0.6307692307692307, "acc_norm_stderr": 0.034648411418637566 }, "community|acva:InfluenceFromIslam|0": { "acc_norm": 0.3310344827586207, "acc_norm_stderr": 0.039215453124671215 }, "community|acva:InfluenceFromPersia|0": { "acc_norm": 0.7085714285714285, "acc_norm_stderr": 0.034449526562290174 }, "community|acva:InfluenceFromRome|0": { "acc_norm": 0.5846153846153846, "acc_norm_stderr": 0.035380132805750295 }, "community|acva:Iraq|0": { "acc_norm": 0.5058823529411764, "acc_norm_stderr": 0.05455069703232772 }, "community|acva:Islam_Education|0": { "acc_norm": 0.48205128205128206, "acc_norm_stderr": 0.035874770987738294 }, "community|acva:Islam_branches_and_schools|0": { "acc_norm": 0.4, "acc_norm_stderr": 0.03713906763541032 }, "community|acva:Islamic_law_system|0": { "acc_norm": 0.4307692307692308, "acc_norm_stderr": 0.0355521325205876 }, "community|acva:Jordan|0": { "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.07446027270295806 }, "community|acva:Kuwait|0": { "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.06666666666666667 }, "community|acva:Lebanon|0": { "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.07106690545187012 }, "community|acva:Libya|0": { "acc_norm": 0.4, "acc_norm_stderr": 0.07385489458759965 }, "community|acva:Mauritania|0": { "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.07535922203472523 }, "community|acva:Mesopotamia_civilization|0": { "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.0402500394824441 }, "community|acva:Morocco|0": { "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.07491109582924914 }, "community|acva:Oman|0": { "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.07491109582924915 }, "community|acva:Palestine|0": { "acc_norm": 0.3058823529411765, "acc_norm_stderr": 0.05027523520585574 }, "community|acva:Qatar|0": { "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.07535922203472523 }, "community|acva:Saudi_Arabia|0": { "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.03581804596782232 }, "community|acva:Somalia|0": { "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.069792059



